专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09043209B2 Language model creation device 有权
标题翻译：语言模型创建设备
公开(公告)号：US09043209B2
公开(公告)日：2015-05-26
申请号：US13129721
申请日：2009-09-03
申请人： Hitoshi Yamamoto , Ken Hanazawa , Kiyokazu Miki
发明人： Hitoshi Yamamoto , Ken Hanazawa , Kiyokazu Miki
IPC分类号： G10L15/14 , G10L15/00 , G10L15/18 , G10L15/197 , G10L15/183 , G10L15/19
CPC分类号： G10L15/197 , G10L15/1815 , G10L15/183 , G10L15/19
摘要： This device 301 stores a first content-specific language model representing a probability that a specific word appears in a word sequence representing a first content, and a second content-specific language model representing a probability that the specific word appears in a word sequence representing a second content. Based on a first probability parameter representing a probability that a content represented by a target word sequence included in a speech recognition hypothesis generated by a speech recognition process of recognizing a word sequence corresponding to a speech, a second probability parameter representing a probability that the content represented by the target word sequence is a second content, the first content-specific language model and the second content-specific language model, the device creates a language model representing a probability that the specific word appears in a word sequence corresponding to a part corresponding to the target word sequence of the speech.
摘要翻译：该设备301存储表示特定词出现在表示第一内容的单词序列中的概率的第一内容特定语言模型和表示特定单词出现在表示一个单词序列的单词序列中的概率的第二特定于内容的语言模型第二个内容。基于表示由语音识别处理生成的语音识别假设所包含的目标字序列表示的内容的概率的第一概率参数，所述概率参数表示识别对应于语音的字序列的语音识别处理，所述第二概率参数表示所述内容由目标词序列表示的是第二内容，第一内容特定语言模型和第二内容特定语言模型，该设备创建表示特定词出现在对应于对应部分的单词序列中的概率的语言模型到目标词序列的演讲。

2. 发明申请

US20110231183A1 LANGUAGE MODEL CREATION DEVICE 有权
标题翻译：语言创作设备
公开(公告)号：US20110231183A1
公开(公告)日：2011-09-22
申请号：US13129721
申请日：2009-09-03
申请人： Hitoshi Yamamoto , Ken Hanazawa , Kiyokazu Miki
发明人： Hitoshi Yamamoto , Ken Hanazawa , Kiyokazu Miki
IPC分类号： G06F17/27
CPC分类号： G10L15/197 , G10L15/1815 , G10L15/183 , G10L15/19
摘要： This device 301 stores a first content-specific language model representing a probability that a specific word appears in a word sequence representing a first content, and a second content-specific language model representing a probability that the specific word appears in a word sequence representing a second content. Based on a first probability parameter representing a probability that a content represented by a target word sequence included in a speech recognition hypothesis generated by a speech recognition process of recognizing a word sequence corresponding to a speech, a second probability parameter representing a probability that the content represented by the target word sequence is a second content, the first content-specific language model and the second content-specific language model, the device creates a language model representing a probability that the specific word appears in a word sequence corresponding to a part corresponding to the target word sequence of the speech.
摘要翻译：该设备301存储表示特定词出现在表示第一内容的单词序列中的概率的第一内容特定语言模型和表示特定单词出现在表示一个单词序列的单词序列中的概率的第二特定于内容的语言模型第二个内容。基于表示由语音识别处理生成的语音识别假设所包含的目标字序列表示的内容的概率的第一概率参数，该概率参数表示识别对应于语音的字序列的语音识别处理，第二概率参数表示内容由目标词序列表示的是第二内容，第一内容特定语言模型和第二内容特定语言模型，该设备创建表示特定词出现在对应于对应部分的单词序列中的概率的语言模型到目标词序列的演讲。

3. 发明申请

US20110161072A1 LANGUAGE MODEL CREATION APPARATUS, LANGUAGE MODEL CREATION METHOD, SPEECH RECOGNITION APPARATUS, SPEECH RECOGNITION METHOD, AND RECORDING MEDIUM 审中-公开
标题翻译：语言模型创作装置，语言模式创作方法，语音识别装置，语音识别方法和记录媒体
公开(公告)号：US20110161072A1
公开(公告)日：2011-06-30
申请号：US13059942
申请日：2009-08-20
申请人： Makoto Terao , Kiyokazu Miki , Hitoshi Yamamoto
发明人： Makoto Terao , Kiyokazu Miki , Hitoshi Yamamoto
IPC分类号： G06F17/27 , G10L15/06
CPC分类号： G06F17/28 , G06F17/2818 , G10L15/183 , G10L15/197
摘要： A frequency counting unit (15A) counts occurrence frequencies (14B) in input text data (14A) for respective words or word chains contained in the input text data (14A). A context diversity calculation unit (15B) calculates, for the respective words or word chains, diversity indices (14C) each indicating the context diversity of a word or word chain. A frequency correction unit (15C) corrects the occurrence frequencies (14B) of the respective words or word chains based on the diversity indices (14C) of the respective words or word chains. An N-gram language model creation unit (15D) creates an N-gram language model (14E) based on the corrected occurrence frequencies (14D) obtained for the respective words or word chains.
摘要翻译：频率计数单元（15A）对包含在输入文本数据（14A）中的各个单词或字链的输入文本数据（14A）中的发生频率（14B）进行计数。上下文分集计算单元（15B）针对各个单词或单词链计算各自指示单词或单词链的上下文分集的分集索引（14C）。频率校正单元（15C）基于各个单词或单词链的分集索引（14C）来校正各个单词或单词链的出现频率（14B）。 N-gram语言模型创建单元（15D）基于针对各个单词或单词链获得的校正出现频率（14D）创建N-gram语言模型（14E）。

4. 发明申请

US20090204390A1 SPEECH PROCESSING APPARATUS AND PROGRAM, AND SPEECH PROCESSING METHOD 有权
标题翻译：语音处理设备和程序，语音处理方法
公开(公告)号：US20090204390A1
公开(公告)日：2009-08-13
申请号：US12306632
申请日：2007-06-18
申请人： Hitoshi Yamamoto , Kiyokazu Miki
发明人： Hitoshi Yamamoto , Kiyokazu Miki
IPC分类号： G06F17/20 , G10L15/04
CPC分类号： G10L15/065 , G10L15/183
摘要： A speech processing apparatus 101 includes a recognition feature extracting unit 12 that extracts recognition feature information which is a characteristic of a speech recognition result 15 obtained by performing a speech recognition process on an inputted speech from the speech recognition result 15; a language feature extracting unit 11 that extracts language feature information which is a characteristic of a pre-registered language resource 14 from the language resource 14; and a model learning unit 13 that obtains a verification model 16 by a learning process based on the extracted recognition feature information and language feature information.
摘要翻译：语音处理装置101包括识别特征提取单元12，其从语音识别结果15提取作为通过对输入的语音执行语音识别处理而获得的语音识别结果15的特征的识别特征信息; 语言特征提取单元11，从语言资源14提取作为预注册语言资源14的特征的语言特征信息; 以及模型学习单元13，其通过基于提取的识别特征信息和语言特征信息的学习处理获得验证模型16。

5. 发明授权

US08583436B2 Word category estimation apparatus, word category estimation method, speech recognition apparatus, speech recognition method, program, and recording medium 有权
标题翻译：词类估计装置，词类估计方法，语音识别装置，语音识别方法，程序和记录介质
公开(公告)号：US08583436B2
公开(公告)日：2013-11-12
申请号：US12809199
申请日：2008-12-19
申请人： Hitoshi Yamamoto , Kiyokazu Miki
发明人： Hitoshi Yamamoto , Kiyokazu Miki
IPC分类号： G06F17/27 , G10L15/00 , G10L15/04 , G10L15/18 , H04M1/64
CPC分类号： G10L15/1815
摘要： A word category estimation apparatus (100) includes a word category model (5) which is formed from a probability model having a plurality of kinds of information about a word category as features, and includes information about an entire word category graph as at least one of the features. A word category estimation unit (4) receives the word category graph of a speech recognition hypothesis to be processed, computes scores by referring to the word category model for respective arcs that form the word category graph, and outputs a word category sequence candidate based on the scores.
摘要翻译：词类别估计装置（100）包括由具有关于词类别的多种信息作为特征的概率模型形成的单词类别模型（5），并且包括关于整个单词分类图的信息作为至少一个的功能。词类估计单元（4）接收要处理的语音识别假设的单词分类图，通过参考形成单词分类图的各弧的单词分类模型来计算分数，并输出基于得分。

6. 发明授权

US08751226B2 Learning a verification model for speech recognition based on extracted recognition and language feature information 有权
标题翻译：基于提取的识别和语言特征信息学习语音识别验证模型
公开(公告)号：US08751226B2
公开(公告)日：2014-06-10
申请号：US12306632
申请日：2007-06-18
申请人： Hitoshi Yamamoto , Kiyokazu Miki
发明人： Hitoshi Yamamoto , Kiyokazu Miki
IPC分类号： G10L15/00 , G10L15/06
CPC分类号： G10L15/065 , G10L15/183
摘要： A speech processing apparatus 101 includes a recognition feature extracting unit 12 that extracts recognition feature information which is a characteristic of a speech recognition result 15 obtained by performing a speech recognition process on an inputted speech from the speech recognition result 15; a language feature extracting unit 11 that extracts language feature information which is a characteristic of a pre-registered language resource 14 from the language resource 14; and a model learning unit 13 that obtains a verification model 16 by a learning process based on the extracted recognition feature information and language feature information.
摘要翻译：语音处理装置101包括识别特征提取单元12，其从语音识别结果15提取作为通过对输入的语音执行语音识别处理而获得的语音识别结果15的特征的识别特征信息; 语言特征提取单元11，从语言资源14提取作为预注册语言资源14的特征的语言特征信息; 以及模型学习单元13，其通过基于提取的识别特征信息和语言特征信息的学习处理获得验证模型16。

7. 发明授权

US09985232B2 Biscarbazole derivative host materials for OLED emissive region 有权
公开(公告)号：US09985232B2
公开(公告)日：2018-05-29
申请号：US14400352
申请日：2012-05-17
申请人： Kazuki Nishimura , Toshihiro Iwakuma , Hitoshi Yamamoto , Michael S. Weaver , Julia J. Brown
发明人： Kazuki Nishimura , Toshihiro Iwakuma , Hitoshi Yamamoto , Michael S. Weaver , Julia J. Brown
IPC分类号： H01L51/00 , H01L51/50 , C07D209/82 , C09K11/06 , C07D401/14 , C07D405/14 , H05B33/20
CPC分类号： H01L51/5016 , C07D209/82 , C07D401/14 , C07D405/14 , C09K11/06 , C09K2211/1007 , C09K2211/1029 , C09K2211/185 , H01L51/0059 , H01L51/0067 , H01L51/0072 , H01L51/0073 , H01L51/0085 , H01L51/5012 , H01L2251/5384 , H05B33/20
摘要： An organic electroluminescence device utilizes a novel combination of one or more biscarbazole derivative compounds as the phosphorescent host material in combination with an organometallic phosphorescent material as a dopant in the light emitting region of the device, where the biscarbazole derivative compounds are represented by a formula (1A) or (2A) below: where A1 represents a substituted or unsubstituted nitrogen-containing heterocyclic group having 1 to 30 ring carbon atoms; A2 represents a substituted or unsubstituted aromatic hydrocarbon group having 6 to 30 ring carbon atoms, or substituted or unsubstituted nitrogen-containing heterocyclic group having 1 to 30 ring carbon atoms; X1 and X2 each are a linking group; Y1 to Y4 each represent a substituent; p and q represent an integer of 1 to 4; and r and s represent an integer of 1 to 3; and the organometallic phosphorescent material is a compound having a substituted chemical structure represented by the formula (4A): where each R is independently selected from the group consisting of H, alkyl, alkenyl, alkynyl, alkylaryl, CN, CF3, CnF2n+1, trifluorovinyl, CO2R, C(O)R, NR2, NO2, OR, halo, aryl, heteroaryl, substituted aryl, substituted heteroaryl or a heterocyclic group; M is a platinum group metal; Ar′, Ar″, Ar′″ and Ar″″ each independently represent a substituted or unsubstituted aryl or heteroaryl substituent on the phenylpyridine ligand; a is 0 or 1; b is 0 or 1; c is 0 or 1; d is 0 or 1; m is 1 or 2; n is 1 or 2; m+n is the maximum number of ligands that can be coordinated to M, and wherein at least one of a, b, c, and d is 1 and when at least one of a and b is 1 and at least one of b and c is 1, at least one of Ar′ and Ar″ is different from at least one of Ar′″ and Ar″″.

8. 发明授权

US09599946B2 Image forming apparatus 有权
公开(公告)号：US09599946B2
公开(公告)日：2017-03-21
申请号：US14847203
申请日：2015-09-08
申请人： Mutsuki Morinaga , Tadashi Kasai , Jun Hitosugi , Takamasa Ozeki , Makoto Yasuda , Kunio Hasegawa , Emiko Shiraishi , Wakana Itoh , Takatsugu Komori , Hitoshi Yamamoto
发明人： Mutsuki Morinaga , Tadashi Kasai , Jun Hitosugi , Takamasa Ozeki , Makoto Yasuda , Kunio Hasegawa , Emiko Shiraishi , Wakana Itoh , Takatsugu Komori , Hitoshi Yamamoto
IPC分类号： G03G15/08 , G03G15/00
CPC分类号： G03G15/553 , G03G15/0849 , G03G15/0853 , G03G15/0856 , G03G2215/0888
摘要： An image forming apparatus includes a latent image bearer, a developing device, a supplier, and a controller. The controller controls the supplier according to a detection result of a toner density by the toner density sensor and a toner density target value to adjust the toner density of developer in the developing device. The controller is configured to correct the toner density target value and an imaging condition affecting a toner adhesion amount of an output image separately from the toner density, according to a component adhesion deterioration degree being a deterioration degree of carrier due to adhesion of a toner component, obtained based on at least an average image area ratio of the output image, and a coating abrasion deterioration degree being a progression degree of deterioration due to coating abrasion of the carrier, obtained based on at least the average image area ratio of the output image.

9. 发明授权

US09513594B2 Protective layer forming device and image forming apparatus 有权
标题翻译：保护层形成装置和成像装置
公开(公告)号：US09513594B2
公开(公告)日：2016-12-06
申请号：US14540745
申请日：2014-11-13
申请人： Kunio Hasegawa , Hiroshi Nakai , Kenji Komito , Tadashi Kasai , Takamasa Ozeki , Jun Hitosugi , Makoto Yasuda , Emiko Shiraishi , Wakana Itoh , Takatsugu Komori , Mutsuki Morinaga , Hitoshi Yamamoto
发明人： Kunio Hasegawa , Hiroshi Nakai , Kenji Komito , Tadashi Kasai , Takamasa Ozeki , Jun Hitosugi , Makoto Yasuda , Emiko Shiraishi , Wakana Itoh , Takatsugu Komori , Mutsuki Morinaga , Hitoshi Yamamoto
IPC分类号： G03G21/00
CPC分类号： G03G21/0094
摘要： A protective layer forming device, including: a powdery image bearer protecting agent formed of a granulated product containing a fatty acid metal salt and an inorganic lubricant; and a roller-shaped protecting agent supplying member configured to supply the powdery image bearer protecting agent to a surface of an image bearer.
摘要翻译：一种保护层形成装置，包括：由含有脂肪酸金属盐和无机润滑剂的造粒产物形成的粉状图像载体保护剂; 以及辊状保护剂供给构件，其构造成将粉状图像载体保护剂供给到图像载体的表面。

10. 发明申请

US20160313668A1 IMAGE FORMING APPARATUS 审中-公开
标题翻译：图像形成装置
公开(公告)号：US20160313668A1
公开(公告)日：2016-10-27
申请号：US15202024
申请日：2016-07-05
申请人： Tadashi KASAI , Makoto Yasuda , Mutsuki Morinaga , Hitoshi Yamamoto , Emiko Shiraishi , Yuichi Aizawa , Takamasa Ozeki , Jun Hitosugi , Kunio Hasegawa , Wakana Itoh , Takatsugu Komori
发明人： Tadashi KASAI , Makoto Yasuda , Mutsuki Morinaga , Hitoshi Yamamoto , Emiko Shiraishi , Yuichi Aizawa , Takamasa Ozeki , Jun Hitosugi , Kunio Hasegawa , Wakana Itoh , Takatsugu Komori
IPC分类号： G03G15/08
CPC分类号： G03G15/0849 , G03G15/0863 , G03G15/0879 , G03G15/55 , G03G2215/0129
摘要： In an image forming apparatus, provided with for each toner category a supply toner conveyance path including, at least as components, a developing means, a toner container corresponding to the developing means, and a connection means corresponding to the developing means and the toner container, each of the components of the supply toner conveyance path being individually replaceable, and includes a toner category detection means configured to detect toner category used in each component; a reporting means configured to report whether toner categories respectively used in all components of the same supply toner conveyance path are the same; and a control means configured to control the reporting means, based on detection information by the toner category detection means, when the component of the supply toner conveyance path is replaced.
摘要翻译：在图像形成设备中，为每个调色剂类别提供一种供应调色剂传送路径，至少包括与显影装置对应的显影装置，显影装置，调色剂容器以及对应于显影装置和调色剂容器的连接装置供给调色剂输送路径的每个部件可单独更换，并且包括配置为检测各部件中使用的调色剂类别的调色剂类别检测装置; 报告装置，被配置为报告分别在同一供应调色剂输送路径的所有部件中使用的调色剂类别是否相同; 以及控制装置，被配置为当更换供应调色剂传送路径的部件时，基于调色剂类别检测装置的检测信息来控制报告装置。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式